Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8022
    Prev
    Next
    INDEX
    Explanations

    compound words or descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neighbours
    -1.09
    Analyse
    -1.02
    programme
    -1.01
    analyse
    -0.95
     أيضاً
    -0.94
    personalised
    -0.94
    Ещё
    -0.94
    cognised
    -0.91
     localised
    -0.91
    ategorised
    -0.90
    POSITIVE LOGITS
     valign
    0.90
     ObjectId
    0.78
    koop
    0.74
    footnotesize
    0.72
    thorpe
    0.71
     осна
    0.70
     Ada
    0.69
    ヨ
    0.69
     FirebaseAuth
    0.69
     acoustic
    0.68
    Activations Density 0.159%

    No Known Activations